{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:05:23Z","timestamp":1775325923044,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T00:00:00Z","timestamp":1688083200000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EY030546"],"award-info":[{"award-number":["R01EY030546"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U24DK112331"],"award-info":[{"award-number":["U24DK112331"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HG009299"],"award-info":[{"award-number":["R01HG009299"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL127349"],"award-info":[{"award-number":["R01HL127349"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL159805"],"award-info":[{"award-number":["R01HL159805"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL157879"],"award-info":[{"award-number":["R01HL157879"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AI04360321"],"award-info":[{"award-number":["R01AI04360321"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"publisher","award":["N6600119C4022"],"award-info":[{"award-number":["N6600119C4022"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2238125"],"award-info":[{"award-number":["2238125"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Sequence-based deep learning approaches have been shown to predict a multitude of functional genomic readouts, including regions of open chromatin and RNA expression of genes. However, a major limitation of current methods is that model interpretation relies on computationally demanding post hoc analyses, and even then, one can often not explain the internal mechanics of highly parameterized models. Here, we introduce a deep learning architecture called totally interpretable sequence-to-function model (tiSFM). tiSFM improves upon the performance of standard multilayer convolutional models while using fewer parameters. Additionally, while tiSFM is itself technically a multilayer neural network, internal model parameters are intrinsically interpretable in terms of relevant sequence motifs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We analyze published open chromatin measurements across hematopoietic lineage cell-types and demonstrate that tiSFM outperforms a state-of-the-art convolutional neural network model custom-tailored to this dataset. We also show that it correctly identifies context-specific activities of transcription factors with known roles in hematopoietic differentiation, including Pax5 and Ebf1 for B-cells, and Rorc for innate lymphoid cells. tiSFM\u2019s model parameters have biologically meaningful interpretations, and we show the utility of our approach on a complex task of predicting the change in epigenetic state as a function of developmental transition.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code, including scripts for the analysis of key findings, can be found at https:\/\/github.com\/boooooogey\/ATAConv, implemented in Python.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad271","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T08:15:30Z","timestamp":1688112930000},"page":"i413-i422","source":"Crossref","is-referenced-by-count":6,"title":["An intrinsically interpretable neural network architecture for sequence-to-function learning"],"prefix":"10.1093","volume":"39","author":[{"given":"Ali Tu\u011frul","family":"Balc\u0131","sequence":"first","affiliation":[{"name":"Joint Carnegie Mellon University-University of Pittsburgh Program in Computational Biology , Pittsburgh, PA 15213, United States"},{"name":"Department of Computational and Systems Biology, University of Pittsburgh , Pittsburgh, PA 15213, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark Maher","family":"Ebeid","sequence":"additional","affiliation":[{"name":"Joint Carnegie Mellon University-University of Pittsburgh Program in Computational Biology , Pittsburgh, PA 15213, United States"},{"name":"Department of Computational and Systems Biology, University of Pittsburgh , Pittsburgh, PA 15213, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panayiotis V","family":"Benos","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, University of Florida , Gainesville, FL 32610, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1460-5487","authenticated-orcid":false,"given":"Dennis","family":"Kostka","sequence":"additional","affiliation":[{"name":"Joint Carnegie Mellon University-University of Pittsburgh Program in Computational Biology , Pittsburgh, PA 15213, United States"},{"name":"Department of Computational and Systems Biology, University of Pittsburgh , Pittsburgh, PA 15213, United States"},{"name":"Department of Developmental Biology, University of Pittsburgh , Pittsburgh, PA 15213, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2550-5403","authenticated-orcid":false,"given":"Maria","family":"Chikina","sequence":"additional","affiliation":[{"name":"Joint Carnegie Mellon University-University of Pittsburgh Program in Computational Biology , Pittsburgh, PA 15213, United States"},{"name":"Department of Computational and Systems Biology, University of Pittsburgh , Pittsburgh, PA 15213, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,6,30]]},"reference":[{"key":"2023063008144585800_btad271-B1","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2023063008144585800_btad271-B2","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1038\/s41592-021-01252-x","article-title":"Effective gene expression prediction from sequence by integrating long-range interactions","volume":"18","author":"Avsec","year":"2021","journal-title":"Nat Methods"},{"key":"2023063008144585800_btad271-B3","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/s41588-021-00782-6","article-title":"Base-resolution models of transcription-factor binding reveal soft motif syntax","volume":"53","author":"Avsec","year":"2021","journal-title":"Nat Genet"},{"key":"2023063008144585800_btad271-B4","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1101\/gr.224436.117","article-title":"Impact of regulatory variation across human iPSCs and differentiated cells","volume":"28","author":"Banovich","year":"2017","journal-title":"Genome Res"},{"key":"2023063008144585800_btad271-B5","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1038\/s41590-021-00980-8","article-title":"Essential role of a ThPOK autoregulatory loop in the maintenance of mature CD4+ T cell identity and function","volume":"22","author":"Basu","year":"2021","journal-title":"Nat Immunol"},{"key":"2023063008144585800_btad271-B6","doi-asserted-by":"crossref","first-page":"10309","DOI":"10.1093\/nar\/gkab765","article-title":"Deciphering enhancer sequence using thermodynamics-based models and convolutional neural networks","volume":"49","author":"Dibaeinia","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023063008144585800_btad271-B7","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"ENCODE Project Consortium","year":"2012","journal-title":"Nature"},{"key":"2023063008144585800_btad271-B8","doi-asserted-by":"crossref","first-page":"4295","DOI":"10.1038\/s41467-019-12348-6","article-title":"ImmGen report: sexual dimorphism in the immune system transcriptome","volume":"10","author":"Gal-Oz","year":"2019","journal-title":"Nat Commun"},{"key":"2023063008144585800_btad271-B9","first-page":"17","volume-title":"Current Topics in Microbiology and Immunology","author":"Hagman","year":"2011"},{"key":"2023063008144585800_btad271-B10","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1038\/nri2476","article-title":"GATA3 and the T-cell lineage: essential functions before and after T-helper-2-cell differentiation","volume":"9","author":"Ho","year":"2009","journal-title":"Nat Rev Immunol"},{"key":"2023063008144585800_btad271-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fimmu.2012.00072","article-title":"Functional differences between human NKp44- and NKp44 RORC innate lymphoid cells","volume":"3","author":"Hoorweg","year":"2012","journal-title":"Front Immun"},{"key":"2023063008144585800_btad271-B12","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1101\/gr.200535.115","article-title":"Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks","volume":"26","author":"Kelley","year":"2016","journal-title":"Genome Res"},{"key":"2023063008144585800_btad271-B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fimmu.2021.732511","article-title":"T-BET and EOMES accelerate and enhance functional differentiation of human natural killer cells","volume":"12","author":"Kiekens","year":"2021","journal-title":"Front Immunol"},{"key":"2023063008144585800_btad271-B14","doi-asserted-by":"crossref","DOI":"10.1084\/jem.20201690","article-title":"The Cxxc1 subunit of the Trithorax complex directs epigenetic licensing of CD4+ T cell differentiation","volume":"218","author":"Kiuchi","year":"2021","journal-title":"J Exp Med"},{"key":"2023063008144585800_btad271-B15","doi-asserted-by":"crossref","first-page":"e1007560","DOI":"10.1371\/journal.pcbi.1007560","article-title":"Representation learning of genomic sequence motifs with convolutional neural networks","volume":"15","author":"Koo","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"2023063008144585800_btad271-B16","doi-asserted-by":"crossref","first-page":"3988","DOI":"10.1182\/blood-2005-05-2003","article-title":"Loss of expression of the hoxa-9 homeobox gene impairs the proliferation and repopulating ability of hematopoietic stem cells","volume":"106","author":"Lawrence","year":"2005","journal-title":"Blood"},{"key":"2023063008144585800_btad271-B17","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1016\/j.immuni.2012.08.001","article-title":"The transcription factors Egr2 and Egr3 are essential for the control of inflammation and antigen-induced proliferation of B and T cells","volume":"37","author":"Li","year":"2012","journal-title":"Immunity"},{"key":"2023063008144585800_btad271-B18","doi-asserted-by":"crossref","first-page":"i499","DOI":"10.1093\/bioinformatics\/btaa506","article-title":"Fully interpretable deep learning model of transcriptional control","volume":"36","author":"Liu","year":"2020","journal-title":"Bioinformatics"},{"key":"2023063008144585800_btad271-B19","doi-asserted-by":"crossref","first-page":"565","DOI":"10.3324\/haematol.2017.185603","article-title":"The many faces of IKZF1 in B-cell precursor acute lymphoblastic leukemia","volume":"103","author":"Marke","year":"2018","journal-title":"Haematologica"},{"key":"2023063008144585800_btad271-B20","doi-asserted-by":"crossref","first-page":"25655","DOI":"10.1073\/pnas.2011795117","article-title":"Deep learning of immune cell differentiation","volume":"117","author":"Maslova","year":"2020","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023063008144585800_btad271-B21","author":"Novakovsky","year":"2022"},{"key":"2023063008144585800_btad271-B22","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1111\/j.1467-9868.2007.00607.x","article-title":"L1-regularization path algorithm for generalized linear models","volume":"69","author":"Park","year":"2007","journal-title":"J R Stat Soc Ser B"},{"key":"2023063008144585800_btad271-B23","author":"Paszke","year":"2019"},{"key":"2023063008144585800_btad271-B24","doi-asserted-by":"crossref","first-page":"e107","DOI":"10.1093\/nar\/gkw226","article-title":"DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences","volume":"44","author":"Quang","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023063008144585800_btad271-B25","doi-asserted-by":"crossref","first-page":"3065","DOI":"10.1182\/blood-2014-03-558825","article-title":"HOXA9 promotes hematopoietic commitment of human embryonic stem cells","volume":"124","author":"Ramos-Mej\u00eda","year":"2014","journal-title":"Blood"},{"key":"2023063008144585800_btad271-B26","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1093\/bioinformatics\/btl565","article-title":"Predicting transcription factor affinities to DNA from a biophysical model","volume":"23","author":"Roider","year":"2007","journal-title":"Bioinformatics"},{"key":"2023063008144585800_btad271-B27","doi-asserted-by":"crossref","first-page":"6649","DOI":"10.4049\/jimmunol.1003703","article-title":"T cell lineage commitment: identity and renunciation","volume":"186","author":"Rothenberg","year":"2011","journal-title":"J Immunol"},{"key":"2023063008144585800_btad271-B28","doi-asserted-by":"crossref","first-page":"5863","DOI":"10.1038\/s41467-021-26159-1","article-title":"Tcf1 and Lef1 provide constant supervision to mature CD8+ T cell identity and function by organizing genomic architecture","volume":"12","author":"Shan","year":"2021","journal-title":"Nat Commun"},{"key":"2023063008144585800_btad271-B29","first-page":"3145","author":"Shrikumar","year":"2017"},{"key":"2023063008144585800_btad271-B30","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s11515-014-1318-y","article-title":"IRF4 and IRF8: governing the virtues of B lymphocytes","volume":"9","author":"Shukla","year":"2014","journal-title":"Front Biol (Beijing)"},{"key":"2023063008144585800_btad271-B31","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1182\/blood.2020009564","article-title":"EBF1 and PAX5 control pro-b cell expansion via opposing regulation of the imyc\/i gene","volume":"137","author":"Somasundaram","year":"2021","journal-title":"Blood"},{"key":"2023063008144585800_btad271-B32","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.75873","article-title":"Macrophage inflammation resolution requires CPEB4-directed offsetting of mRNA degradation","volume":"11","author":"Su\u00f1er","year":"2022","journal-title":"eLife"},{"key":"2023063008144585800_btad271-B33","doi-asserted-by":"crossref","first-page":"1603","DOI":"10.1093\/bioinformatics\/btr257","article-title":"Improved similarity scores for comparing motifs","volume":"27","author":"Tanaka","year":"2011","journal-title":"Bioinformatics"},{"key":"2023063008144585800_btad271-B34","author":"Tareen","year":"2019"},{"key":"2023063008144585800_btad271-B35","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1016\/j.cell.2014.08.009","article-title":"Determination and inference of eukaryotic transcription factor sequence specificity","volume":"158","author":"Weirauch","year":"2014","journal-title":"Cell"},{"key":"2023063008144585800_btad271-B36","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/ni.3456","article-title":"TCF1 and LEF1 transcription factors establish CD8+ T cell identity through intrinsic HDAC activity","volume":"17","author":"Xing","year":"2016","journal-title":"Nat Immunol"},{"key":"2023063008144585800_btad271-B37","first-page":"24365","volume-title":"Advances in Neural Information Processing Systems","author":"Yun","year":"2021"},{"key":"2023063008144585800_btad271-B38","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning-based sequence model","volume":"12","author":"Zhou","year":"2015","journal-title":"Nat Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i413\/50741446\/btad271.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i413\/50741446\/btad271.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T08:16:03Z","timestamp":1688112963000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/39\/Supplement_1\/i413\/7210441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":38,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2023,6,30]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad271","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,6,1]]}}}